Fix chat CLI GPU loading and request_id validation issues (#40230) #40232
+1
−1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
cc @gante |
gante
reviewed
Aug 18, 2025
There was a problem hiding this comment.
Thank you for diving into the issues @robin-ede 🤗
One small change and it's good to go 💛
…e#40230) This commit addresses two critical bugs in the transformers chat CLI: 1. **GPU Loading Issue**: Changed default device from "cpu" to "auto" in ChatArguments - Chat CLI now automatically uses GPU when available instead of defaulting to CPU - Matches the behavior of the underlying serving infrastructure 2. **Request ID Validation Error**: Added request_id field to TransformersCompletionCreateParamsStreaming schema - Fixes "Unexpected keys in the request: {'request_id'}" error on second message - Allows request_id to be properly sent and validated by the server Both fixes target the exact root causes identified in issue huggingface#40230: - Users will now get GPU acceleration by default when available - Chat sessions will no longer break after the second message
robin-ede
force-pushed
the
fix-chat-cli-issues-40230
branch
from
2a9ab45 to
ca5908e
Compare
|
@gante fixed! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
This PR fixes two critical bugs in the
transformers chatCLI that prevent users from using chat:Issue 1: Chat CLI doesn't use GPU by default
Problem: The chat CLI was defaulting to CPU inference even when GPUs are available, leading to slow performance.
Root Cause: The
deviceparameter inChatArgumentswas hardcoded to"cpu"instead of"auto".Solution: Changed the default from
"cpu"to"auto"insrc/transformers/commands/chat.py:249to match the serving backend behavior.Issue 2: Chat breaks on second message with validation error
Problem: After the first message, subsequent messages fail with error:
"Unexpected keys in the request: {'request_id'}"Root Cause: The chat client sends a
request_idfield in the request body, but the server's validation schema (TransformersCompletionCreateParamsStreaming) doesn't recognize this field as valid.Solution: Added
request_id: Optional[str] = Noneto the schema insrc/transformers/commands/serving.py:128to allow this field to pass validation.Testing
ruff check,ruff format)Fixes #40230
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?